12 Jul 2017
10:30
A103
S1: Smart City – Applications
| 1. Comparison of Cogent Confabulation Based,Classifier and Naive Bayes Classifier in the Detection of Lens Flares in, Wildfire Smoke Detection | ||
| Maja Braović, Darko Stipaničev, Dunja Gotovac and Damir Krstinić (University of Split, Croatia) | ||
| In wildfire smoke detection various spatial and temporal procedures are,used to detect certain wildfire features. The final step is usually the,classification procedure that finally decides if some detected phenomena,represents wildfire smoke or not. In classification procedure various,classifiers can be used, but as the system has to work in real time and,usually on limited hardware, the efforts of researchers working on those,systems are usually aimed towards the implementation of classifiers,that are simple for implementation and fast in execution. In this paper,the emphasis is on the comparison of two simple and fast classifiers -,the cogent confabulation based classifier and the Naive Bayes,classifier. Even though they can appear similar, on the theoretical and,philosophical level they are quite different. Beside the theoretical,comparison of both classifiers they are also compared on an example of,lens flare detection in images taken from wildfire smoke surveillance,cameras video streams. | ||
| 2. Model for Automatic Geomapping of Aerial Images Mosaic Acquired by UAV | ||
| Dunja Gotovac, Sven Gotovac, Vladan Papić and Stanko Kružić (University of Split, Croatia) | ||
| In this paper, we proposed a novel approach for an automatic aerial,image georeferencing for an unmanned aerial vehicle (UAV) image data,acquisition platform that does not require the use of ground control,points (GCP’s). The determination of GCP’s is, in general, a costly and,slow process, hence a considerable bottleneck in georeferencing. With,predefined route planning and making a mosaic of acquired aerial images,,we managed to calculate world file transformation. In comparison with,manual collecting GCP’s, our automatic georeferenced results indicated,that position errors were less than 92 cm. This accuracy is considered,sufficient for most of the intended precision for search and rescue,purposes. | ||
| 3. Opportunities, Risks and Challenges of using Social Media to foster Smart Governance for Smart Cities | ||
| Nuno Vasco Lopes (University of Minho, Portugal); Mariana Lameiras (United Nations University, Portugal) |
||
| Social media are increasingly used for different purposes, ranging from,attempts to reach wider audiences, to attract different publics, to,propose alternative means for interaction with citizens and/or other,stakeholders. Apparently, there is an immense list of possibilities and,there is potential to explore social media as one of the vehicles for,providing smart governance for smart cities taking into account,governance principles such as openness (i.e. transparency),,accountability, collaboration (i.e. involvement of all stakeholders) and,participatory processes (i.e. citizens’ participation). This paper identifies the challenges, opportunities, and risks of social,media usage for smart cities to foster smart governance based on the,scientific literature. Although we did not find many scientific papers,about the role of social media for smart governance, interesting,possibilities are addressed. In addition, there is a lack of empirical,work. Our conclusions point out that we are in the infancy of this,field, taking the first steps in leveraging the potential of social,media on smart governance. |
||
| 4. A Smart Algorithm to Relief Traffic Congestion | ||
| Nasima Bhuiyan (California State University, Long Beach, USA) | ||
| The objective of the study is to develop an efficient travel management,model to generate a smart transportation corridor system to mitigate,congestion which will prevent, or minimize traffic delays on urban,freeways. Based on a first order partial differentiation (PDE) method,via a “continuum” approach this study l develops a mathematical model,which will capture the sensitivity of cascading behavior of motorists,subscribing to congestion downstream. Using simulation, the density of,traffic on freeways can be estimated by calculating the number of smart,connected vehicles escaping through the nearest off ramp during the time,of congestion. The model validation will be carried out using a,simulation of cascading scenarios with traffic data for I-405 freeway,(with exit ramps) and its surrounding roadway network in the corridor at,Southern California region. | ||
| 5. ArduTalk: A Graphical Programming tool for Arduino using IoTtalk | ||
| Yun-Wei Lin (National Chiao Tung University, Taiwan) | ||
| Many Internet of Things (IoT) technologies interconnect physical,sensors, actuators, and heterogeneous computing devices within the,existing Internet infrastructure, which make our life more convenient.,ArduTalk is a graphical programming environment based on IoTtalk, which,aims to develop internetworking Arduino applications for multiple,Arduino boards. Therefore, sensors and actuators can be plugged in,different Arduino boards, and the user can utilize ArduTalk to,arbitrarily link and re-link sensors to actuators to create different,applications for different purposes, which is a very convenient way to,develop IoT applications especially for beginners. Performance,measurement shows that the actuator still has a quick response time when,the actuator is triggered by a sensor through ArduTalk. |